Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens (digits or numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Μπ
    -0.06
     SOC
    -0.06
    跟
    -0.06
    送料無料
    -0.06
     abych
    -0.06
    hist
    -0.06
    physical
    -0.06
    _logging
    -0.06
    (listener
    -0.06
     histogram
    -0.06
    POSITIVE LOGITS
    ahir
    0.07
    ject
    0.07
    styleType
    0.07
    rement
    0.07
    .Gray
    0.07
     ویژه
    0.07
    _draw
    0.06
    /material
    0.06
    _lt
    0.06
    вод
    0.06
    Act Density 0.074%

    No Known Activations